rohunvora

Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.

Build a design system from scratch using the Design Graph methodology. Use when starting a component library, creating design tokens, establishing typography scales, or structuring a theme. Based on Brent Jackson's (jxnblk) constraint-based systems.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.

Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.

This skill should be used when user wants to learn from their collected references, synthesize patterns across sources, or turn research into frameworks from curated reference collections (Are.na channels, bookmarks, saved articles).

This skill should be used to fix visual hierarchy when everything looks equally important, CTAs don't stand out, or users miss key information. Applies Von Restorff Effect, Serial Position Effect, and Law of Prägnanz.

This skill should be used when elements feel disconnected, cards float like islands, or groupings are unclear. Applies Law of Proximity, Law of Common Region, and Law of Uniform Connectedness.

This skill should be used when building single-file browser applications, client-side utilities, or interactive tools that need no backend. Covers patterns for state persistence, API integration, and advanced browser capabilities without React or build steps.

This skill should be used when users drop off mid-task, motivation fades, or experiences feel flat. Applies Peak-End Rule, Goal-Gradient Effect, and Zeigarnik Effect.

Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

Use this skill when writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

Generate minimal HTML pages to review Claude Code output in a browser. Use when terminal output is hard to read, when reviewing lists/tables/drafts, or when user says "show me", "make this reviewable", "quick view", or "open as webpage". Produces unstyled semantic HTML only.

This skill should be used when the user is stuck, obvious solutions aren't working, constraints feel impossible, or they keep circling back to bad options. Use when designs keep getting rejected or the user is solving symptoms instead of root causes.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use when building anything non-trivial. Enforces a spec → plan → execute → verify loop that prevents "looks right" failures. Creates spec.md, todo.md, and decisions.md before writing code.

Structure an app around objects when starting a complex app from scratch, existing navigation feels messy, users can't find things, or the IA is getting worse as features are added. Use Object-Oriented UX to design around nouns, not verbs.

Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating, optimizing, or reducing agent tool sets.

Analyze and improve UI density using Matt Ström's 4-dimensional framework. Use when interfaces feel too sparse, too cluttered, or when users complain about efficiency.